Although wikis are common in both the workplace and in Higher Education, little research has studied the wiki user experience. Recent literature highlights that users may be anxious about editing wiki content; yet in most of this research this anxiety has not been measured quantitatively. Although computer anxiety metrics exist to measure anxiety towards technology, they lack specificity and relevance to the wiki editing context. This paper reports two studies used to research the validity and reliability of the wiki anxiety inventory-editing (WAI-E), an inventory developed and used to measure anxiety in wiki editing (Study 1) and to explore the factor structure of the WAI-E and the validity and reliability of the resulting subscales (Study 2). Study 1 shows that the WAI-E, when used as a uni-dimensional structure, shows high reliability and validity. The principal component analysis conducted in Study 2 showed that the measure converged on a three-factor solution with factors measuring positive affect, editability anxiety and contribution judgement anxiety. The subscales showed high reliability and validity. It therefore seems that although the validity and reliability of using the WAI-E as a uni-dimensional construct are high, the use of the metric as such hides the true structure and nuances of the concept of wiki anxiety.

With the advent of Web 2.0, the number of IT systems used in university courses is growing. Yet research consistently shows that a significant proportion of students are anxious about computer use. The quality of first experience with computers has been consistently mentioned as a significant contributor to anxiety onset. However the effect of users’ first experience on system related anxiety has not to the authors’ knowledge been researched using controlled experiments. Indeed little experiment based research has been conducted on the wiki user experience, specifically users’ evaluations and emotional reactions towards editing. This research uses usability engineering principles to engineer four different wiki experiences for novice wiki users and measures the effect each has on usability, anxiety during editing and on anxiety about future wiki editing. Each experience varied in the type of training spaces available before completing six live wiki editing tasks. We found that anxiety experienced by users was not related to computer anxiety but was wiki specific. Users in the in-built tutorial conditions also rated the usability of the editing interface higher than users in the non-tutorial conditions. The tutorial conditions also led to a significant reduction in wiki anxiety during interaction but did not significantly affect future editing anxiety. The findings suggest that the use of an in-built tutorial reduces emotional and technological barriers to wiki editing and that controlled experiments can help in discovering how aspects of the system experience can be designed to affect usability and anxiety towards editing wikis.

This paper describes an experiment to investigate the usability of voiceprints for customer authentication in automated telephone banking. The usability of voiceprint authentication using digits (random strings and telephone numbers) and sentences (branded and unbranded) are compared in a controlled experiment with 204 telephone banking customers. Results indicate high levels of usability and customer acceptance for voiceprint authentication in telephone banking. Customers find voiceprint authentication based on digits more usable than that based on sentences, and a majority of participants would prefer to use digits.

Multi-factor authentication involves the use of more than one mode in authentication processes and is typically employed to increase security compared to a fixed password (knowledge-based mode). This research compared three different eBanking authentication processes, a two-layer password (1-factor) method and two alternative 2-factor solutions. The 2-factor processes used One-Time-Passcodes (OTPs) delivered either via a small, single-use device or by text message to a mobile phone. The three authentication methods were compared in a repeated-measures experiment with 141 participants. Three user groups were balanced in the experiment to investigate the effect of experience (current users of the service) on perceptions of usability and security. Attitudes toward usability and observations were taken for each process. Other data gathered quality ratings, preferences and ranked comparisons regarding convenience and security issues. Both 2-factor methods scored significantly higher than the 1-factor method for eBanking authentication usability metrics overall, but experienced users gave higher scores to the 1-factor method they currently use. Overall preferences were spread evenly between the three methods. However, the majority of the participant sample perceived the 1-factor method they had most experience with as being the most secure and most convenient option. The results offer insight into customer attitudes important in their selection of authentication options: convenience, personal ownership and habitual experience of processes.

Abstract The SPELL (Spoken Electronic Language Learning) system is a self‐access computer‐assisted language learning (CALL) package that integrates speaker‐independent continuous speech recognition technology with virtual worlds and embodied virtual agents to create an environment in which learners can converse in the target language within meaningful contextualized scenarios. In this paper we provide an overview of the functionality, architecture, and implementation of the SPELL system. We also describe four phases of usability evaluation conducted with the system and summarize the main results of these user assessments. Finally, we discuss the most significant lessons learned in the development and evaluation of the system. The paper focuses on the technological aspects of the system and its evaluation for usability and robustness, rather than its pedagogical methodology. Copyright © 2008 John Wiley & Sons, Ltd.

This paper explores the consequences of adopting an alternative strategy to that of explicitly listing all options within the main menu of a speech-driven automated telephone banking service. An existing service was augmented with an overdraft request dialogue, accessible at its main menu, which could be triggered using the keyword “overdraft”. However, the keyword was not explicitly mentioned as an option in the main menu. Instead, system-initiated proposals for an overdraft were introduced into the call flow, notifying callers that they could apply for an overdraft by saying “overdraft” at the main menu. An experiment with 114 participants was carried out to investigate the effectiveness of this strategy as a way of offering new services without increasing the length of the main menu. Results showed that a significant proportion of participants (37%) did not succeed in completing an overdraft request. The reasons for this failure are discussed.

The current Internet Banking (eBanking) marketplace is highly functionally convergent. Electronic statement (eStatement) functionality is an area of potential competitive advantage. This paper describes an experiment in which a group of bank customers (N = 182) undertook information retrieval tasks using three variants of eStatements functionality incorporated into a working eBanking prototype. The experiment examined how the eStatements service design could influence a customer’s desire to switch from paper statements to online delivery. Three different levels of functionality were assessed for usability and for their impact on the customer’s willingness to switch from paper to eStatements. The methodology of the experimental approach utilised in this research is described. The results provide detailed data to inform the interface design and business case for eStatements. Usability and propensity to switch away from paper were significantly correlated. The data confirm that provision of a functionally sophisticated search engine offers high usability perceptions and scope for significant levels of switching from paper to online statements with associated costs savings.

Results are reported from two usability trials in which a total of 14 schemes for alphanumeric data entry on television screens were evaluated. The seven schemes in the first trial used only the navigation and select keys on the TV remote control unit. The second trial used the best scheme from the first trial (slightly modified), a further six schemes using different combinations of the navigation and alphanumeric keys and a portable, infra-red keyboard. In both trials task completion rates and times were measured together with the number of keystrokes. User preferences were measured using attitude questionnaires and explicit ranking of the schemes. As expected, the keyboard was, overall, the best scheme-though not the most accurate. Where only a limited range of input keys were available, grid display schemes were preferred over menus and dynamic displays. Where an alphanumeric keypad was available on the remote control unit, a multiple press scheme was marginally preferred.

This paper addresses the problem of temporal constraints in the Viterbi algorithm in speaker-dependent and independent tasks. The results here presented suggest that in a speaker-dependent task the introduction of temporal constraints can lead to a high improvement with additive or convolutional noise, the statistical modeling of state durations is not relevant if the max and min state duration restrictions are imposed, and truncated probability densities give better results than a metric previously proposed. Finally, word position dependent and independent temporal restrictions are compared in connected word speech recognition experiments and it is shown that the former leads to better results with the same computational load. However the duration model effect could be much less significant when the acoustic model is optimized and when the training and testing conditions are matched.

This paper presents three experiments designed to empirically evaluate humanoid synthetic agents in electronic retail applications. First, human-like agents were evaluated in a single e-retail application, a home furnishings service. The second experiment explored application dependency effects by evaluating the same human-like agents in a different e-retail application, a personalized CD service. The third experiment evaluated the effectiveness of a range of humanoid cartoon-like agents. Participants eavesdropped on spoken dialogues between a "customer" and each of the agents, which played the role of conversational sales assistants. Results showed participants expected a high level of realistic human-like verbal and nonverbal communicative behavior from the human-like agents. Overall ratings of the agents showed no significant application dependency. Further results showed participants have a preference for 3D rather than 2D cartoon-like agents and have a desire to interact with fully embodied agents.

This paper presents a new approach to tone modeling for continuous Mandarin speech recognition. Mandarin tones provide rich information for speech recognition. In this paper, we treat the tone as an attribute of the final vowel part of a Mandarin syllable. Separate distributions are estimated for cepstral coefficients and pitch features respectively, and the phonetic state tied-mixture technique is exploited to achieve improved modeling. Several tying structures are investigated, and the results are compared with that without using tonal parameters. After integrating tone models, decent improvements can be achieved in large vocabulary continuous Mandarin speech recognition. Besides, this approach can be easily incorporated into the one-pass Viterbi search framework for practical implementation of Mandarin dictation system.

A weighted Viterbi algorithm (HMM) is proposed and applied in combination with spectral subtraction and cepstral mean normalization to cancel both additive and convolutional noise in speech recognition. The weighted Viterbi approach is compared and used in combination with state duration modelling. The results presented show that a proper weight on the information provided by static parameters can substantially reduce the error rate, and that the weighting procedure improves better the robustness of the Viterbi algorithm than the introduction of temporal constraints with a low computational load. Finally, it is shown that the weighted Viterbi algorithm in combination with temporal constraints leads to a high recognition accuracy at moderate SNRs without the need of an accurate noise model.

Until now, the possibility of a 'virtual mannequin' service for telepresence shopping systems has been unrealistic due to the number and complexity of calculations required for the modelling of physical clothing items. This paper presents an overview of the FIGMENT scheme (Fast Implementation Garment Modelling environmENT) which incorporates a four-point strategy (a simplified physical model, collision volume approximation, progressive meshes and a hybrid rendering algorithm) to reduce the quantity and complexity of the computations involved, bringing simulation times from the realm of hours to minutes and seconds whilst maintaining an acceptable level of accuracy and fidelity in the results.

This paper reports an experiment to investigate users' preferences amongst three modes of data entry in an automated home shopping service: DTMF input on the telephone keypad, and isolated word (IW) and connected word (CW) speech input. Preferences were measured both by means of attitude questionnaires and by giving participants an explicit choice among the three versions of the service once they had experienced them all. Users' attitudes to the service with a given mode of data entry were found to vary according to their cognitive skills (verbal and spatial abilities) and according to whether they had previously experienced a different data entry mode. Overall, DTMF and CW were rated similarly, and were strongly preferred to IW. Implications of these findings for the implementation of telephone-based services are discussed.

Addresses the problem of speech recognition with signals corrupted by additive noise at moderate signal-to-noise ratio (SNR). A model for additive noise is presented and used to compute the uncertainty about the hidden clean signal so as to weight the estimation provided by spectral subtraction. Weighted dynamic time warping (DTW) and Viterbi (HMM) algorithms are tested, and the results show that weighting the information along the signal can substantially increase the performance of spectral subtraction, an easily implemented technique, even with a poor estimation for noise and without using any information about the speaker. It is also shown that the weighting procedure can reduce the error rate when cepstral mean normalization is also used to cancel the convolutional noise.

This paper addresses the problem of speech recognition with signals corrupted by additive noise at moderate SNR. A technique based on spectral subtraction and noise cancellation reliability weighting in acoustic pattern matching algorithms is studied. A model for additive noise is proposed and used to compute the variance of the hidden clean signal information and the reliability of the spectral subtraction process. The results presented show that a proper weight on the information provided by static parameters can substantially reduce the error rate.

The multi-mutation rates, multi-crossover rates and a scheme of reinitialization are applied to parallel genetic algorithm for assigning the codevector indices for noisy channels for the purpose of minimizing the distortion caused by bit errors.Experimental results based on the memoryless binary symmetric channel for any bit error demonstrate the robustness of this new approach compared with our previous work [1].The property o f m ultiple global optima is also emphasized in this paper.

The problems of ecacy estimation in noise cancelling by a neural net ) and the use of this information in weighting matching algorithms are focused.Since the eect of noise on the speech signal is variable and the backpropagation training algorithm is essentially stochastic (most common patterns have more inuence in the weights re-estimation process), it is reasonable to suppose that the LIN ecacy depends on the input and each noisy frame could be associated to a reliability coecient that attempts to measure how reliable is the result of the neural net processing.Isolated word recognition experiments have shown that reliability weighting can result in a mean error rate reduction as high as 96, 80, 58 and 36 % at SNR=12, 6, 3 and 0dB, respectively, when the noise is white Gaussian.

This paper describes the use of a multiple codebook SCHMM speaker verification system, which uses a novel technique for discriminative hidden Markov modelling known as discriminative observation probabilities (DOP). DOP can easily be added to a multiple codebook HMM system and require minimal additional computation and no additional training. The DOP technique can be applied to both speech and speaker recognition. Results are presented for text-dependent experiments on isolated digits from 27 true speakers and 84 casual imposters, recorded over the public telephone network in the United Kingdom. DOP are shown to significantly improve speaker verification performance for several commonly used parameter sets.>

A comparative evaluation of several pitch determination algorithms (PDAs) is presented. Fundamental frequency estimates, F0, are compared with laryngeal frequency estimates, Lx. An algorithm is presented which enables Lx contours to be generated from laryngograph data. We seek the most accurate method of FO extraction in order to minimise errors propagating into subsequent prosodic analysis. The super resolution pitch determinator [S] performs well relative to the other PDAs studied. Modifications made to this algorithm are described, which radically reduce the number of gross F0 errors and improve the classification of voiced and unvoiced sections of speech. The raw F0 contours produced by this enhanced algorithm are processed to form schematised contours used in computer aided intonation teaching. The series of processes used in the schematisation is described.

This paper details the standards identified for phonetic transcription of names as part of the ONOMASTICA project, a European-wide research initiative for the construction of a multi-language pronunciation lexicon of proper names. The main design criteria adopted by the consortium for the development of this multi-language pronunciation dictionary are discussed, including aspects such as phonetic transcription standards, definitions of quality, quality control mechanisms and language specific details concerning phonetic transcription and the annotation of the language of origin.

A real-time continuous speech recognition system based on the Inmos transputer is developed. The recognition algorithm is described in detail, and the hardware architecture of the system (which incorporates the AT&T DSP32-C and Inmos T800 transputers) is also described. The implementation of the hidden Markov model recognition algorithm in parallel form is presented. The system has been built using readily available hardware, and it operates using an IBM-PC host, providing real-time speaker-dependent recognition for aircraft movement and spreadsheet control applications.>

A report is presented of comparative results for vowel classification using hidden Markov models based on linear predictive coding (LPC)-based cepstral vectors and formant features. The classification accuracy is shown to be significantly improved by using time duration constraints in formant feature space, especially for the formant mel-frequency representation and its time derivative. The highest vowel recognition accuracy is obtained by integrating the two feature spaces, multiplying the probabilities computed in the separate feature spaces. This improvement of vowel recognition is extended to the more general phoneme recognition task by use of a hierarchical feature integration method, which utilizes the vowel recognition results in formant feature space together with consonant recognition based on the LPC-based cepstral feature space.>

A semicontinuous hidden Markov model (HMM), which can be considered as a special form of continuous-mixture HMM with the continuous output probability density functions sharing in a mixture Gaussian density codebook, is proposed. The semicontinuous output probability density function is represented by a combination of the discrete output probabilities of the model and the continuous Gaussian density functions of a mixture Gaussian density codebook. The amount of training data required, as well as the computational complexity of the semicontinuous HMM, can be reduced in comparison to the continuous-mixture HMM. Parameters of the codebook and HMM can be mutually optimized to achieve an optimal model/codebook combination, which leads to a unified modeling approach to vector quantization and hidden Markov modeling of speech signals. Experimental results are included which show that the recognition accuracy of the semicontinuous HMM is measurably higher than those of both the discrete and the continuous HMM.>

The technique presented, termed pole focusing, provides an approach to obtaining high-resolution formant data from the short-time spectrum. Formant estimation is based on modeling the vocal tract frequency response using linear prediction coding (LPC) techniques. However, the pole-focusing technique is the antithesis of standard LPC analysis, in that large model orders are used and preemphasis is not required. The technique involves averaging over several spectral estimates within any single analysis frame, which also aids in conferring very high noise immunity to the estimation process.>

A technique termed pole focusing is presented that provides a novel approach to obtained high-resolution formant data for pattern recognition processing of the short-time speech spectrum. The technique offers reliable detection of weak nasal formants and formants undergoing rapid transitions in frequency, areas where parametric spectral analysis typically performs poorly. Much of the recognition of speech using a feature-based approach relies heavily on the detection of formant time-frequency trajectory patterns, which gives the identification not only for the voiced speech sound currently under analysis, but also can provide important cues to pre- and postvocalic speech. The enhanced formant detection properties offered by pole focusing therefore can considerably improve the reliability of formant pattern recognition.>

A robust speech-analysis method based on an adaptive weighted least-squares lattice algorithm is introduced to improve the performance of conventional frame-based linear predictive coding analysis. The likelihood variable, which can be considered as a statistic measure of nonGaussian components, is used to de-weight the excitation interval. The likelihood variable can also be considered as a useful statistic for detecting outliers. Short analysis windows, with optimal frame position placement determined according to local minimum of the likelihood variable and residual, are adopted to mimic glottis-closure analysis. Experiments on both synthetic speech and real speech are included to show that the algorithm offers improved formant estimation accuracy in comparison to the frame-based method.>

A semicontinuous hidden Markov model is proposed to incorporate the vector quantization distortion into the general hidden Markov model methodology under a probabilistic framework. It provides a relatively simple but powerful tool for modeling time-varying signal sources. Experimental results show that the recognition accuracy of the semi-continuous model is measurably improved in comparison to that of the conventional discrete hidden Markov model and template-based dynamic time warping techniques.>

Recent work on the representation of 'knowledge' in massively parallel networks has resulted in the development of the Boltzmann Machine. In such networks, 'knowledge' is represented by the pattern and strengths of interconnections between simple processing elements. In the Boltzmann Machine noise is used to aid the search procedure in the network. Developed primarily for static image processing, Boltzmann Machines are well suited to problems that can be formulated as constraint satisfaction searches. This paper describes some simple experiments using a Boltzmann Machine to process and classify static speech patterns.